深度神经网络自适应中基于身份认证向量的归一化方法

doi:10.7523/j.issn.2095-6134.2017.05.014

中国科学院大学学报 ›› 2017, Vol. 34 ›› Issue (5): 633-639.DOI: 10.7523/j.issn.2095-6134.2017.05.014

深度神经网络自适应中基于身份认证向量的归一化方法

杨建斌, 张卫强, 刘加

清华大学电子工程系, 北京 100084

收稿日期:2016-07-19 修回日期:2016-10-13 发布日期:2017-09-15
通讯作者: 张卫强,E-mail:wqzhang@tsinghua.edu.cn
基金资助:
国家自然科学基金（61370034，61403224）资助

Investigation of normalization methods in speaker adaptation of deep neural network using i-vector

YANG Jianbin, ZHANG Weiqiang, LIU Jia

Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Received:2016-07-19 Revised:2016-10-13 Published:2017-09-15

摘要/Abstract

摘要： 深度神经网络是近年来非常流行的一种语音识别声学建模技术，其性能比之前主流的高斯混合模型有显著提高，但是深度神经网络的说话人自适应技术一直没有很好地解决。利用身份认证向量对深度神经网络进行自适应，并研究身份认证向量归一化对系统的影响，提出一种新的max-min线性归一化技术。实验表明在TIMIT数据集上该技术可使字错误率比传统方法相对下降5.10%。

关键词: 身份认证向量, 深度神经网络, 说话人自适应, 归一化

Abstract: The deep neural network (DNN) was a remarkable modeling technology for speech recognition in recent years and its performance was significantly better than that of the Gaussian mixture model,which was the mainstream modeling technology in speech recognition before.However,commendable adaptation of DNN has not been solved yet.In this work,we use the identity vector (i-vector) to adapt a deep neural network by putting i-vector and the regular speech features together as the input of DNN for both training and testing.Then we focus on the normalization method of i-vector using a new max-min linear normalization method.We get a 5.10%relative decrease in word error rate over the traditional length normalization method.

Key words: identity vector, deep neural network, speaker adaptation, normalization

中图分类号:

TN912

杨建斌, 张卫强, 刘加. 深度神经网络自适应中基于身份认证向量的归一化方法[J]. 中国科学院大学学报, 2017, 34(5): 633-639.

YANG Jianbin, ZHANG Weiqiang, LIU Jia. Investigation of normalization methods in speaker adaptation of deep neural network using i-vector[J]. , 2017, 34(5): 633-639.

参考文献

[1] 李虎生, 刘加, 刘润生. 语音识别说话人自适应研究现状及发展趋势[J]. 电子学报, 2003, 31(1):103-108.
[2] Hinton G E, Osindero S, Toh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527.
[3] 孙志军, 薛磊, 许阳明, 等. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8):2806-2810.
[4] Abdel-Hamid O, Jiang H. Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code//Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. IEEE, 2013:7942-7946.
[5] Seide F, Li G, Chen X, et al. Feature engineering in context-dependent deep neural networks for conversational speech transcription//Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on. IEEE, 2011:24-29.
[6] Gemello R, Mana F, Scanzio S, et al. Adaptation of hybrid ANN/HMM models using linear hidden transformations and conservative training//Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on. IEEE, 2006:1189-1192.
[7] Gupta V, Kenny P, Ouellet P, et al. i-Vector-based speaker adaptation of deep neural networks for french broadcast audio transcription//Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on. IEEE, 2014:6334-6338.
[8] 栗志意.i-vector说话人识别建模关键技术与实用化研究.北京:清华大学,2014.
[9] Dehak N, Kenny P, Dehak R, et al. Front-end factor analysis for speaker verification[J]. Audio, Speech, and Language Processing, IEEE Transactions on, 2011, 19(4):788-798.
[10] Torbati A H H N, Picone J. A doubly hierarchical Dirichlet process hidden Markov model with a non-ergodic structure[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016, 24(1):174-184.
[11] Chen J, Wu L, Audhkhasi K, et al. Efficient one-vs-one kernel ridge regression for speech recognition//2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2016:2454-2458.
[12] Sailor H B, Patil H A. Filterbank learning using Convolutional Restricted Boltzmann Machine for speech recognition//2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2016:5895-5899.
[13] Ghahremani P, Droppo J, Seltzer M L. Linearly augmented deep neural network//2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2016:5085-5089.

深度神经网络自适应中基于身份认证向量的归一化方法

Investigation of normalization methods in speaker adaptation of deep neural network using i-vector

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	王慧玲, 谢卓辰, 梁旭文. 单粒子翻转对神经网络的影响分析与优化[J]. 中国科学院大学学报, 2021, 38(6): 832-840.
[2]	王健飞, 张卫强, 刘加. 基于多状态跳转模型的场景独立音频事件检测方法[J]. 中国科学院大学学报, 2019, 36(2): 218-225.
[3]	冷晓旭, 肖俊. 一种基于Haar小波和归一化的鲁棒零水印算法[J]. 中国科学院大学学报, 2013, 30(3): 410-416.
[4]	袁大洋王颖. 基于边信息抗仿射变换的数字图像水印算法[J]. 中国科学院大学学报, 2007, 24(1): 86-92.
[5]	赵辉, 董宝中, 董宇辉. 北京同步辐射装置小角散射站实验数据归一化[J]. 中国科学院大学学报, 2002, 19(4): 433-435.